Paper Citation Record · LEDGER

Lifelong Knowledge Editing requires Better Regularization

As of 10 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 2 inbound Pith citation observations for arXiv:2502.01636.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.01636 v2

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T14:46:55.228337Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:50:53.345156Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-16T09:30:48.102328Z

Reference resolution

14 of 14 outbound references displayed

verified exact1
verified fuzzy10
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 44a1a8db-e4ae-4f18-906d-900358d8dddc · outbound

This paper cites It is calculated as the percentage of edits where P (new fact) > P (old fact) when evaluated on paraphrases of the query prompt.

Lifelong Knowledge Editing requires Better Regularization It is calculated as the percentage of edits where P (new fact) > P (old fact) when evaluated on paraphrases of the query prompt

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.505444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 28e18be6-162e-428e-9b26-6c28db2d9f95 · outbound

This paper cites Specifically, it is the percentage of edits where P (new fact) > P(old fact) for paraphrased versions of the query prompt.

Lifelong Knowledge Editing requires Better Regularization Specifically, it is the percentage of edits where P (new fact) > P(old fact) for paraphrased versions of the query prompt

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.489631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f82a2fca-bcb2-48cc-8cc4-dcaff705eb73 · outbound

This paper cites It is the percentage of unaffected facts in the neighborhood of the edited fact.

Lifelong Knowledge Editing requires Better Regularization It is the percentage of unaffected facts in the neighborhood of the edited fact

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.473316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ba99abf7-dfd0-4ec4-97d8-8b1dbce8f220 · outbound

This paper cites GE is computed as the weighted average of bi-gram and tri-gram entropies in the text gen- erated by the edited model.

Lifelong Knowledge Editing requires Better Regularization GE is computed as the weighted average of bi-gram and tri-gram entropies in the text gen- erated by the edited model

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.456791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 162591b1-1e46-412a-90e9-a080b8c12021 · outbound

This paper cites It is calculated as the harmonic mean of the Efficacy Score (ES), Paraphrase Score (PS), and Neighborhood Score (NS).

Lifelong Knowledge Editing requires Better Regularization It is calculated as the harmonic mean of the Efficacy Score (ES), Paraphrase Score (PS), and Neighborhood Score (NS)

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.438963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4783b4a9-2bea-4212-9ce0-5abe0a7f1bcf · outbound

This paper cites These are the facts that the model learnt through its pre-training.

Lifelong Knowledge Editing requires Better Regularization These are the facts that the model learnt through its pre-training

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.422675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ee7e1b34-59fa-4214-8c7c-54eeae880720 · outbound

This paper cites This is the standard baseline case with- out MPES.

Lifelong Knowledge Editing requires Better Regularization This is the standard baseline case with- out MPES

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.406600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8994c05d-d288-4949-9263-5225ac073519 · outbound

This paper cites In this case we used LTI during editing the fact.

Lifelong Knowledge Editing requires Better Regularization In this case we used LTI during editing the fact

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.390293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 12104873-3082-412c-8979-e67cfb71ac16 · outbound

This paper cites In this case, MPES is used during editing the fact.

Lifelong Knowledge Editing requires Better Regularization In this case, MPES is used during editing the fact

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.374336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2ad65e38-db53-448b-b317-86d0852b856a · outbound

This paper cites Tables 6, 7 and 8 show the hyperparameters for CounterFact dataset and tables 9,10 and 11 show the hyperparameters for the zsRE dataset.

Lifelong Knowledge Editing requires Better Regularization Tables 6, 7 and 8 show the hyperparameters for CounterFact dataset and tables 9,10 and 11 show the hyperparameters for the zsRE dataset

Reference 14

Resolution: verified exact; raw_fallback, observed 2026-08-09T14:47:10.308838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bf00c5a7-0a73-4b09-b343-8ada69826aac · outbound

This paper cites Editing Factual Knowledge in Language Models.

Lifelong Knowledge Editing requires Better Regularization Editing Factual Knowledge in Language Models

Reference 2005

Resolution: unresolved; no resolver link, observed 2026-08-09T14:46:55.164430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6f3af66-3551-4cbb-8369-edfad6f46a53 · outbound

This paper cites In Proceedings of the Second PAS- CAL Challenges Workshop on Recognising Textual Entailment, volume 7, pages 785–794.

Lifelong Knowledge Editing requires Better Regularization In Proceedings of the Second PAS- CAL Challenges Workshop on Recognising Textual Entailment, volume 7, pages 785–794

Reference 2006

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:47:10.522656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 96388c42-2252-4055-bfe3-3523a4346cbd · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Lifelong Knowledge Editing requires Better Regularization Measuring Massive Multitask Language Understanding

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T14:46:55.180747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 394b61cd-3b97-4509-b30b-4b256038b29b · outbound

This paper cites AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models.

Lifelong Knowledge Editing requires Better Regularization AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-09T14:46:55.170807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 28bff15b-602c-4afc-b3f5-9264a5168727 · inbound

Efficient Knowledge Editing via Minimal Precomputation cites this paper.

Efficient Knowledge Editing via Minimal Precomputation Lifelong Knowledge Editing requires Better Regularization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T10:50:53.345156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9107a2e0-d63e-4f3b-af17-f14940f4bab8 · inbound

Norm Anchors Make Model Edits Last cites this paper.

Norm Anchors Make Model Edits Last Lifelong Knowledge Editing requires Better Regularization

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-16T09:30:48.105174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.